Accurate Event-based eye tracking for resource-constrained devices.

This paper presents an innovative pipeline to eye-tracking with computational efficiency, utilizing a fully event-based algorithm. Traditional eye-tracking methods often rely on grayscale or infrared imaging, which can be computationally intensive and raise privacy concerns. Our research addresses these issues by developing an algorithm that exclusively uses data from event-based sensors, optimizing for settings with limited computational power. The system relies on simple geometrical operations, enabling efficient real-time processing. Experimental results demonstrate the feasibility of this approach, offering a promising solution for eye-tracking in compact, computationally constrained devices.